Example Vectra image analysis
Loading packages
library(cowplot)
library(ggplot2)
source('spatstat_vectra.R')
plot_function <- function(csd, ctypes) {
plt <- ggplot() + theme_bw() +
geom_point(data = csd[grep('Other', csd$Phenotype),],
aes(x=x, y=y), col = '#b5b3ae', size=2.5) +
geom_point(data = csd[csd$Phenotype%in%c('PAX5+PDL1-','PAX5+PDL1+'),],
aes(x=x, y=y), col = '#fc8105', size=2.5) +
geom_point(data = csd[grep('PAX5+PDL1+', csd$Phenotype, fixed=T),],
aes(x=x, y=y), col = '#fff761', size=0.01, shape=1, stroke=1) +
geom_point(data = csd[grep('CD3+CD8-',csd$Phenotype, fixed=T),],
aes(x=x, y=y), col = '#34c9eb', size=2.5) +
geom_point(data = csd[grep('CD3+CD8+',csd$Phenotype, fixed=T),],
aes(x=x, y=y), col = '#4634eb', size=2.5) +
geom_point(data = csd[grep('PD1+', csd$Phenotype, fixed=T),],
aes(x=x, y=y), col = '#fff761', size=0.01,shape=1, stroke=1) +
geom_point(data = csd[grep('CD163', csd$Phenotype),],
aes(x=x, y=y), col = '#a834eb', size=2.5) +
geom_point(data = csd[grep('CD163+PDL1+', csd$Phenotype, fixed=T),],
aes(x=x, y=y), col = '#fff761', size=0.01, shape=1, stroke=1)
return(plt +theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank()))
}Example images (5 images)
images = c(
'exported_mIF/HO105-003_[11564,35679]_cell_seg_data.txt',
'exported_mIF/HO105-003_[11564,35679]_cell_seg_data.txt',
'exported_mIF/HO105-025_[9621,46812]_cell_seg_data.txt',
'exported_mIF/HO105-182_[8076,47954]_cell_seg_data.txt',
'exported_mIF/HO105-020_[9758,38701]_cell_seg_data.txt'
)
ctypepairs = list(
c('CD3+CD8-PD1-', 'CD8+CD8-PD1+', 'CD3+CD8+PD1-', 'CD3+CD8+PD1+'),
c('CD163+PDL1-', 'CD163+PDL1+', 'CD3+CD8+PD1-', 'CD3+CD8+PD1+'),
c('CD163+PDL1-', 'CD163+PDL1+'),
c('CD163+PDL1-', 'CD163+PDL1+'),
c('CD163+PDL1-', 'CD163+PDL1+')
)
XposCol = 'Cell X Position'
YposCol = 'Cell Y Position'
PhenoCol = 'Phenotype'
#i=1
for (i in 1:length(images)) {
plist = list()
Table <- purrr::map_df(images[i], read_cell_seg_data,
pixels_per_micron = "auto", remove_units=FALSE)
# replace empty phenotype with "Other"
Table$Phenotype[Table$Phenotype == ""] = "Other"
# define csd for ppp
csd <- as.data.frame(Table[, c(PhenoCol, XposCol, YposCol)])
colnames(csd) = c('Phenotype', 'x', 'y')
plt1 <- local({
plt1 = plot_function(csd, c('Tumor', 'Tcell', 'Macrophage', 'Other'))
#plt <- plt + ggtitle(images[i])
plt1 <- plt1 + #ggtitle(images[i]) +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
axis.title.x=element_blank(), axis.text.x=element_blank(),
axis.ticks.x=element_blank(), axis.title.y=element_blank(),
axis.text.y=element_blank(), axis.ticks.y=element_blank(),
panel.background = element_blank()) + ggtitle('all cell types')# + scale_y_reverse()
return(plt1)
})
#print(plt1)
xlims <- layer_scales(plt1)$x$get_limits()
ylims <- layer_scales(plt1)$y$get_limits()
csd2 <- csd
plt2 <- plot_function(csd2[csd2$Phenotype%in%ctypepairs[[i]],],
c('Tumor', 'Tcell', 'Macrophage', 'Other')) +
xlim(xlims) + ylim(ylims)# + scale_y_reverse()
plt2 <- plt2 +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
axis.title.x=element_blank(), axis.text.x=element_blank(),
axis.ticks.x=element_blank(), axis.title.y=element_blank(),
axis.text.y=element_blank(), axis.ticks.y=element_blank(),
panel.background = element_blank()) +
ggtitle(paste0('focus: ', paste0(ctypepairs[[i]], collapse='/')))# + scale_y_reverse()
plot_row <- plot_grid(plt1, plt2)
title <- ggdraw() +
draw_label(
images[i],
fontface = 'bold',
x = 0,
hjust = 0
) +
theme(
plot.margin = margin(0,0,0,7)
)
print(plot_grid(title, plot_row, ncol=1, rel_heights = c(0.1,1)))
}
## Reading cell seg data with comma separator.
Visualization of the images
phenotype_complete = c("CD163+PDL1-","CD163+PDL1+",
"CD3+CD8-PD1-", "CD3+CD8-PD1+", "CD3+CD8+PD1-", "CD3+CD8+PD1+",
"Other","Other PDL1+", "PAX5+PDL1-", "PAX5+PDL1+", "")
color_complete = list("magenta", "brown",
"red", "blue", "green", "yellow",
"gray", "pink", "orange", "cyan", "gray")
names(color_complete) = phenotype_complete
fig.prefix.complete = './complete'
selected_spatstat_statistics = c('K', 'L')
# can be any subset of ('K', 'Kdot', 'L', 'Ldot', 'F', 'J', 'G', 'Gdot', 'pcf')
r_vec = c(5, 10, 25, 50, 75, 100)
plotter_sample = T
plotter_quadrat = T
plotter_alltypes = T
plotter = list(plotter_sample, plotter_quadrat, plotter_alltypes)
outputs_complete = list()
for (file in images){
cat('processing', file)
samplename = gsub('_cell_seg_data.txt', '', tail(strsplit(file, '/')[[1]],1))
outputs_complete[[samplename]] = do_analyse(seg_path = file, PhenoOrder = phenotype_complete,
ColsOrder = color_complete, XposCol = 'Cell X Position',
YposCol = 'Cell Y Position', PhenoCol = 'Phenotype',
sample_name = samplename, plotter = plotter, fig.prefix = fig.prefix.complete,
r_vec = r_vec, spatstat_statistics = selected_spatstat_statistics)
}## processing exported_mIF/HO105-003_[11564,35679]_cell_seg_data.txtdimensions of the data with distances is 2638 times 210## Other PAX5+PDL1- CD3+CD8-PD1- CD163+PDL1- CD3+CD8+PD1- CD3+CD8-PD1+ CD3+CD8+PD1+
## 488 1240 586 216 95 11 2## computing K of alltypes
## Computing limits## interpolating K
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## computing L of alltypes
## Computing limits## interpolating L
## significance band width is 0, instead normalizing by width_eps = 10^(-5).
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## processing exported_mIF/HO105-003_[11564,35679]_cell_seg_data.txtdimensions of the data with distances is 2638 times 210## Other PAX5+PDL1- CD3+CD8-PD1- CD163+PDL1- CD3+CD8+PD1- CD3+CD8-PD1+ CD3+CD8+PD1+
## 488 1240 586 216 95 11 2## computing K of alltypes
## Computing limits## interpolating K
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## computing L of alltypes
## Computing limits## interpolating L
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## processing exported_mIF/HO105-025_[9621,46812]_cell_seg_data.txtdimensions of the data with distances is 1833 times 214## Other PAX5+PDL1- CD163+PDL1+ CD3+CD8-PD1- Other PDL1+ CD3+CD8+PD1+ CD3+CD8+PD1- CD3+CD8-PD1+ CD163+PDL1-
## 533 569 566 50 79 1 24 10 1## computing K of alltypes
## Computing limits## interpolating K
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## significance band width is 0, instead normalizing by width_eps = 10^(-5).
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## significance band width is 0, instead normalizing by width_eps = 10^(-5).
## significance band width is 0, instead normalizing by width_eps = 10^(-5).
## significance band width is 0, instead normalizing by width_eps = 10^(-5).
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## significance band width is 0, instead normalizing by width_eps = 10^(-5).
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## computing L of alltypes
## Computing limits## interpolating L
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## significance band width is 0, instead normalizing by width_eps = 10^(-5).
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## significance band width is 0, instead normalizing by width_eps = 10^(-5).
## significance band width is 0, instead normalizing by width_eps = 10^(-5).
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## significance band width is 0, instead normalizing by width_eps = 10^(-5).
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## processing exported_mIF/HO105-182_[8076,47954]_cell_seg_data.txtdimensions of the data with distances is 1151 times 212## PAX5+PDL1+ PAX5+PDL1- CD163+PDL1+ CD3+CD8+PD1- Other CD163+PDL1- CD3+CD8-PD1+ CD3+CD8-PD1-
## 90 643 105 48 108 126 2 29## computing K of alltypes
## Computing limits## interpolating K
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## computing L of alltypes
## Computing limits## interpolating L
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## NA in calculating significance bands so width significance band is infinit, normalized statistic set to 0.
## processing exported_mIF/HO105-020_[9758,38701]_cell_seg_data.txtdimensions of the data with distances is 1362 times 210## Other CD163+PDL1+ PAX5+PDL1- CD3+CD8-PD1+ CD3+CD8-PD1- CD163+PDL1- PAX5+PDL1+
## 65 144 1002 9 84 57 1## computing K of alltypes
## Computing limits## interpolating K
## significance band width is 0, instead normalizing by width_eps = 10^(-5).
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## computing L of alltypes
## Computing limits## interpolating L
## significance band width is 0, instead normalizing by width_eps = 10^(-5).
## significance band width is 0, instead normalizing by width_eps = 10^(-5).
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NA
## NA or NaN 'obs': too few counts in observed pattern to compute centered and normalized statistic, both set to NAThe script do_analyse measures multiple statistics
(K and L statistics were chosen in the example
above) for the given image (seg_path). Apart from the
statistics itself, it will save images at the location specified by
fig.prefix. One example image (K statistics) of all pairs
of cell types considered (defined by PhenoOrder) is shown
below. Note that + and - signs are converted
to T and F. The red line and gray shadow
indicate theoretical statistics when the pair of cell types have no
geometric association. The solid black line represents the actual
statistic.
Example image
Creating a feature matrix
Feature matrix can be created with feature_extract
function.
mat = feature_extract(outputs_complete)## begin feature extraction
## end feature extractiondf = data.frame(feature = colnames(mat), stringsAsFactors=F)
# some features are excluded in the study
keyword_exclude = c('counts_sample', 'counts_lognormed', 'counts_pairwise', 'counts_pairwise',
'density_lognormed', 'density_lognormed', 'Ldot_', 'Kdot_', 'pcf_')
df$Use = rep(TRUE, ncol(mat))
for (key in keyword_exclude) {
df$Use[grep(key, colnames(mat))] = FALSE
}
# unnormalized spatial features were also excluded
ind_unnormalized = setdiff(grep('radius', df$feature), grep('Normalized', df$feature))
df[ind_unnormalized, 'Use'] = FALSE
# feature annotation
df$celltype = unlist(lapply(df$feature, function(x) tail(strsplit(x, '_', fixed=T)[[1]],1)))
df$celltype = unlist(lapply(df$celltype,
function(x) paste0(sort(strsplit(x, '/')[[1]]), collapse='/')
))
feat_key = c(count='counts_[a-z]+', density='density_', Xstat='X2stat_[a-z]', MedianDistance='MED|distance_ratio',
RelDistance = 'Relative_distance', MADDistance='MAD', Fstat='F_radius', Gstat='G_radius|Gdot_radius',
Kstat='K_radius|Kdot_radius', Lstat='L_radius|Ldot_radius', PCFstat='pcf_radius')
ctype_key = grep('counts_sample', df$feature, value=T)
ctype_key = unlist(lapply(ctype_key, function(x) tail(strsplit(x, '_', fixed=T)[[1]], 1)))
df$feat_group = NA
for (i in 1:length(feat_key)) {
df$feat_group[grep(feat_key[i], df$feature)] = names(feat_key)[i]
}
for (i in 1:length(ctype_key)) {
df[[ctype_key[i]]] = FALSE
df[[ctype_key[i]]][grep(ctype_key[i], df$feature, fixed=T)] = TRUE
for (overlap in setdiff(grep(ctype_key[i], ctype_key, value=T, fixed=T), ctype_key[i])) {
df[[ctype_key[i]]][grep(overlap, df$feature, fixed=T)] = FALSE
}
}
for (radius in c(5,10, 25, 50, 75, 100, 150, 200, 250, 500)) {
ind = grep(paste0('radius ', as.character(radius), '_'), df$feature)
df$feat_group[ind] = paste0(df$feat_group[ind], ', r=', as.character(radius))
}
#Feature overview
color = c(
"NonSpatial" = "#72ac5c",
"GlobalSpatial" = "#7f64b9",
"LocalSpatial" = "#bb7438",
"Poisson, r_5" = "#c2215f",
"Poisson, r_10" = "#c76f90",
"Poisson, r_25" = "#da9eb4",
"Poisson, r_50" = "#e2b2c3",
"Poisson, r_75" = "#f2dee5",
"Poisson, r_100" = "#f7ecf0",
"Poisson, local" = "#c2215f",
"Poisson, global" = "#e2b2c3"
)
freq = data.frame(table(df[df$Use, ]$feat_group))
ftypes = list(
NonSpatial=c("count", "density"),
GlobalSpatial=c("MAD_Distance", "Median_Distance", 'Xstat'),
LocalSpatial=c("MAD_Min_Distance", "Median_Min_Distance", "RelDistance")
)
radius = list(local=c(5, 10, 25), global=c(50, 75, 100))
for (r in 1:length(radius)) {
feats = c()
for (rs in radius[[r]]) {
feats = c(feats, grep(paste0('r=', as.character(rs), '$'), df$feat_group, value=T))
}
ftypes[[paste0('Poisson, ',names(radius)[r])]] = unique(feats)
}
freq$category = NA
for (i in 1:length(ftypes)){
freq$category[freq$Var1%in%ftypes[[i]]] = names(ftypes)[i]
}
freq$category = factor(freq$category, levels =names(ftypes))
freq$Feat = unlist(lapply(freq$Var1, function(x) strsplit(as.character(x), ',')[[1]][1]))
freq$Feat = gsub('_', ' ', freq$Feat, fixed=T)
freq$Var1 = factor(freq$Var1, levels=freq$Var1[order(freq$category)])
freq$Feat = factor(freq$Feat, levels=unique(freq$Feat[order(freq$category)]))
ggplot(freq[!is.na(freq$category),], aes(x=Feat, y=Freq, fill=category)) + geom_bar(stat='identity') + theme_bw() +
theme(axis.text.x = element_text(angle=90, vjust=1, hjust=1)) + scale_fill_manual(values=color) +
xlab("Feature type") + ylab("# of features")
Session Information
sessionInfo()## R version 4.0.0 (2020-04-24)
## Platform: x86_64-conda_cos6-linux-gnu (64-bit)
## Running under: CentOS Linux 7 (Core)
##
## Matrix products: default
## BLAS/LAPACK: /home/y.kim1/anaconda2/envs/Vectra/lib/libopenblasp-r0.3.12.so
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8 LC_MONETARY=fr_FR.UTF-8 LC_MESSAGES=en_US.UTF-8 LC_PAPER=fr_FR.UTF-8
## [8] LC_NAME=C LC_ADDRESS=C LC_TELEPHONE=C LC_MEASUREMENT=fr_FR.UTF-8 LC_IDENTIFICATION=C
##
## attached base packages:
## [1] grid stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] VIM_6.2.2 colorspace_2.1-0 Rtsne_0.16 survminer_0.4.9 ggpubr_0.2.5 magrittr_2.0.3 readxl_1.4.2 sp_1.5-0
## [9] latex2exp_0.9.5 reshape2_1.4.4 RColorBrewer_1.1-3 phenoptr_0.3.2 tiff_0.1-11 remotes_2.4.2 spdep_1.2-8 sf_0.9-5
## [17] spData_2.2.0 spatstat_3.0-3 spatstat.linnet_3.0-6 spatstat.model_3.2-1 rpart_4.1.16 spatstat.explore_3.1-0 nlme_3.1-150 spatstat.random_3.1-4
## [25] spatstat.geom_3.1-0 spatstat.data_3.0-1 forcats_1.0.0 stringr_1.5.0 dplyr_1.1.1 purrr_1.0.1 readr_2.1.4 tidyr_1.3.0
## [33] tibble_3.2.1 tidyverse_1.3.2 ggplot2_3.4.1 cowplot_1.1.1 rmarkdown_2.21 nvimcom_0.9-102
##
## loaded via a namespace (and not attached):
## [1] backports_1.4.1 plyr_1.8.7 splines_4.0.0 digest_0.6.31 foreach_1.5.2 htmltools_0.5.5 fansi_1.0.4 tensor_1.5
## [9] googlesheets4_1.0.1 tzdb_0.3.0 modelr_0.1.11 vroom_1.6.1 timechange_0.2.0 spatstat.sparse_3.0-1 rvest_1.0.3 haven_2.5.2
## [17] xfun_0.38 crayon_1.5.2 jsonlite_1.8.4 survival_3.4-0 zoo_1.8-11 iterators_1.0.14 glue_1.6.2 polyclip_1.10-4
## [25] gtable_0.3.3 gargle_1.2.1 car_3.1-0 DEoptimR_1.0-11 abind_1.4-5 scales_1.2.1 DBI_1.1.3 Rcpp_1.0.9
## [33] laeken_0.5.2 xtable_1.8-4 units_0.8-0 bit_4.0.5 proxy_0.4-27 km.ci_0.5-6 vcd_1.4-10 httr_1.4.4
## [41] wk_0.6.0 pkgconfig_2.0.3 farver_2.1.1 nnet_7.3-17 sass_0.4.5 dbplyr_2.3.2 deldir_1.0-6 utf8_1.2.3
## [49] tidyselect_1.2.0 labeling_0.4.2 rlang_1.1.0 munsell_0.5.0 cellranger_1.1.0 tools_4.0.0 cachem_1.0.6 cli_3.6.1
## [57] generics_0.1.3 ranger_0.14.1 broom_1.0.4 evaluate_0.20 fastmap_1.1.1 yaml_2.3.7 goftest_1.2-3 knitr_1.42
## [65] bit64_4.0.5 fs_1.6.1 robustbase_0.93-6 survMisc_0.5.6 s2_1.1.0 xml2_1.3.3 compiler_4.0.0 e1071_1.7-11
## [73] ggsignif_0.6.3 spatstat.utils_3.0-2 reprex_2.0.2 bslib_0.4.2 stringi_1.7.12 highr_0.10 lattice_0.20-45 Matrix_1.4-1
## [81] classInt_0.4-3 KMsurv_0.1-5 vctrs_0.6.1 pillar_1.9.0 lifecycle_1.0.3 lmtest_0.9-38 jquerylib_0.1.4 data.table_1.14.2
## [89] R6_2.5.1 KernSmooth_2.23-18 gridExtra_2.3 codetools_0.2-18 boot_1.3-28 MASS_7.3-58.1 withr_2.5.0 mgcv_1.8-40
## [97] parallel_4.0.0 hms_1.1.3 class_7.3-20 carData_3.0-5 googledrive_2.0.0 lubridate_1.9.2